{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NKKPQQ6GYZBCD4BNFQ3B24GZMS","short_pith_number":"pith:NKKPQQ6G","canonical_record":{"source":{"id":"2404.06078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-09T07:32:55Z","cross_cats_sorted":[],"title_canon_sha256":"a3fde7b752fcf4badf43e540c6b354481a6ba37eb60255be6a09ce59d51a6f4d","abstract_canon_sha256":"4f869115c016c11d305946c548d1d871a5a098cfebb2e6867bf7fa993650b461"},"schema_version":"1.0"},"canonical_sha256":"6a94f843c6c64221f02d2c361d70d964bff10e298227d3ac7c2816ec7b06ea6b","source":{"kind":"arxiv","id":"2404.06078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06078","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06078v1","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06078","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"NKKPQQ6GYZBC","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"NKKPQQ6GYZBCD4BN","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"NKKPQQ6G","created_at":"2026-07-05T08:06:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NKKPQQ6GYZBCD4BNFQ3B24GZMS","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-09T07:32:55Z","cross_cats_sorted":[],"title_canon_sha256":"a3fde7b752fcf4badf43e540c6b354481a6ba37eb60255be6a09ce59d51a6f4d","abstract_canon_sha256":"4f869115c016c11d305946c548d1d871a5a098cfebb2e6867bf7fa993650b461"},"schema_version":"1.0"},"canonical_sha256":"6a94f843c6c64221f02d2c361d70d964bff10e298227d3ac7c2816ec7b06ea6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:03.397185Z","signature_b64":"DOsGIMOvXuk7wOPFQb4Qi5E3vtqAk7Dk+SpHPY9J53rPddNz5u5OVZ5siPWq6zHkBFQ9yAMimMTh8UJ7EoPBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a94f843c6c64221f02d2c361d70d964bff10e298227d3ac7c2816ec7b06ea6b","last_reissued_at":"2026-07-05T08:06:03.396655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:03.396655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06078","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7VGorBz8DbyEvNcH906SeiA2ZKjspVwgKrJgG60x2l+42YhjuniQaBCmvpwlcdvq+77MTSe6RDokruAlO4dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:28.557772Z"},"content_sha256":"1c5a46054cdbfac76b41b35c58e90d934bf02303508df96b3d60529f823c45f5","schema_version":"1.0","event_id":"sha256:1c5a46054cdbfac76b41b35c58e90d934bf02303508df96b3d60529f823c45f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NKKPQQ6GYZBCD4BNFQ3B24GZMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-end training of Multimodal Model and ranking Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Di Zhang, Erpeng Xue, Guorui Zhou, Han Li, Jinkai Yu, Lu Xu, Na Mou, Shen Jiang, Xiuqi Deng, Xiyao Li, Yang Song, Zhaojie Liu, Zhongyuan Wang","submitted_at":"2024-04-09T07:32:55Z","abstract_excerpt":"Traditional recommender systems heavily rely on ID features, which often encounter challenges related to cold-start and generalization. Modeling pre-extracted content features can mitigate these issues, but is still a suboptimal solution due to the discrepancies between training tasks and model parameters. End-to-end training presents a promising solution for these problems, yet most of the existing works mainly focus on retrieval models, leaving the multimodal techniques under-utilized. In this paper, we propose an industrial multimodal recommendation framework named EM3: End-to-end training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06078","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.06078/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XfTURE32AdIqyIoor3pLX7DPHFZSsQYGkaI59sBjQnTl0lKallKZ+2G9YLw0vYWZik6Vs2QUsa7wbJ5aMguaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:28.558717Z"},"content_sha256":"a1f40268b08c30acca05755cce46c067c2daee0827f3adb105dc5face9907604","schema_version":"1.0","event_id":"sha256:a1f40268b08c30acca05755cce46c067c2daee0827f3adb105dc5face9907604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/bundle.json","state_url":"https://pith.science/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T15:30:28Z","links":{"resolver":"https://pith.science/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS","bundle":"https://pith.science/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/bundle.json","state":"https://pith.science/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKKPQQ6GYZBCD4BNFQ3B24GZMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NKKPQQ6GYZBCD4BNFQ3B24GZMS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4f869115c016c11d305946c548d1d871a5a098cfebb2e6867bf7fa993650b461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-09T07:32:55Z","title_canon_sha256":"a3fde7b752fcf4badf43e540c6b354481a6ba37eb60255be6a09ce59d51a6f4d"},"schema_version":"1.0","source":{"id":"2404.06078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06078","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06078v1","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06078","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"NKKPQQ6GYZBC","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"NKKPQQ6GYZBCD4BN","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"NKKPQQ6G","created_at":"2026-07-05T08:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:a1f40268b08c30acca05755cce46c067c2daee0827f3adb105dc5face9907604","target":"graph","created_at":"2026-07-05T08:06:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.06078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional recommender systems heavily rely on ID features, which often encounter challenges related to cold-start and generalization. Modeling pre-extracted content features can mitigate these issues, but is still a suboptimal solution due to the discrepancies between training tasks and model parameters. End-to-end training presents a promising solution for these problems, yet most of the existing works mainly focus on retrieval models, leaving the multimodal techniques under-utilized. In this paper, we propose an industrial multimodal recommendation framework named EM3: End-to-end training ","authors_text":"Di Zhang, Erpeng Xue, Guorui Zhou, Han Li, Jinkai Yu, Lu Xu, Na Mou, Shen Jiang, Xiuqi Deng, Xiyao Li, Yang Song, Zhaojie Liu, Zhongyuan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-09T07:32:55Z","title":"End-to-end training of Multimodal Model and ranking Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06078","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c5a46054cdbfac76b41b35c58e90d934bf02303508df96b3d60529f823c45f5","target":"record","created_at":"2026-07-05T08:06:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4f869115c016c11d305946c548d1d871a5a098cfebb2e6867bf7fa993650b461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-09T07:32:55Z","title_canon_sha256":"a3fde7b752fcf4badf43e540c6b354481a6ba37eb60255be6a09ce59d51a6f4d"},"schema_version":"1.0","source":{"id":"2404.06078","kind":"arxiv","version":1}},"canonical_sha256":"6a94f843c6c64221f02d2c361d70d964bff10e298227d3ac7c2816ec7b06ea6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a94f843c6c64221f02d2c361d70d964bff10e298227d3ac7c2816ec7b06ea6b","first_computed_at":"2026-07-05T08:06:03.396655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:03.396655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOsGIMOvXuk7wOPFQb4Qi5E3vtqAk7Dk+SpHPY9J53rPddNz5u5OVZ5siPWq6zHkBFQ9yAMimMTh8UJ7EoPBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:03.397185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c5a46054cdbfac76b41b35c58e90d934bf02303508df96b3d60529f823c45f5","sha256:a1f40268b08c30acca05755cce46c067c2daee0827f3adb105dc5face9907604"],"state_sha256":"071f635fcf32d8af9da47e53516cf42a218bc71b2b89c806e8c9d28b7d008a23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLzedcMBQK+j2V3MuSSWJAGNdiIKlygcyIusOkvviFB/qqKnnSou4TxYelpvIUt9CYgxNPwAS5RtVMXLSHEABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:30:28.564054Z","bundle_sha256":"e79a897c32f99c59be0974a0c4686c9a4e98f270431e863420b9835548a3e77c"}}